10,000,000 token context makes it a fit for large prompts, transcripts, documents, and repositories.
- text
- image
- tools
- structured
This page ranks live models by usable context window first, then pricing and capability support, so you can shortlist models for large documents, repositories, transcripts, and agent memory.
Long context matters when prompts include large codebases, long documents, meeting transcripts, or multi-file retrieval results that would otherwise need chunking or repeated calls.
TVP refreshes this page from the live OpenRouter model catalog. This render used 428 public model records and was synchronized Jul 14, 2026, 9:34 PM UTC. Pricing, availability, and context values can change.
Verify the exact route before sending production traffic, then use the linked model and provider pages as the source for current values. Read the TVP data methodology.
10,000,000 token context makes it a fit for large prompts, transcripts, documents, and repositories.
2,000,000 token context makes it a fit for large prompts, transcripts, documents, and repositories.
2,000,000 token context makes it a fit for large prompts, transcripts, documents, and repositories.
1,050,000 token context makes it a fit for large prompts, transcripts, documents, and repositories.
1,050,000 token context makes it a fit for large prompts, transcripts, documents, and repositories.
Long context matters when prompts include large codebases, long documents, meeting transcripts, or multi-file retrieval results that would otherwise need chunking or repeated calls.
No. Very large context is helpful only if the model quality and price still fit the workload. Some teams do better with a smaller context model plus retrieval.
TVP keeps the shortlist connected to the current catalog, provider coverage, and token pricing so buyers can move from research to routing without starting over.